中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

134 records (took 0.035 seconds)

    RECORDING MEDIUM, POLICY IMPROVING METHOD, AND POLICY IMPROVING APPARATUS
    82.
    发明申请
    RECORDING MEDIUM, POLICY IMPROVING METHOD, AND POLICY IMPROVING APPARATUS 审中-公开

    公开(公告)号：US20190086876A1

    公开(公告)日：2019-03-21

    申请号：US16130469

    申请日：2018-09-13

    Applicant: FUJITSU LIMITED ,  Okinawa Institute of Science and Technology School Corporation

    Inventor： Tomotake Sasaki ,  Eiji Uchibe ,  Kenji Doya ,  Hirokazu Anai ,  Hitoshi Yanami ,  Hidenao Iwane

    IPC: G05B13/02 ,  G06F15/18 ,  G06F17/16

    Abstract: A non-transitory, computer-readable recording medium stores a program of reinforcement learning by a state-value function. The program causes a computer to execute a process including calculating a TD error based on an estimated state-value function, the TD error being calculated by giving a perturbation to each component of a feedback coefficient matrix that provides a policy; calculating based on the TD error and the perturbation, an estimated gradient function matrix acquired by estimating a gradient function matrix of the state-value function with respect to the feedback coefficient matrix for a state of a controlled object, when state variation of the controlled object in the reinforcement learning is described by a linear difference equation and an immediate cost or an immediate reward of the controlled object is described in a quadratic form of the state and an input; and updating the feedback coefficient matrix using the estimated gradient function matrix.

    INVERSE REINFORCEMENT LEARNING BY DENSITY RATIO ESTIMATION
    90.
    发明申请
    INVERSE REINFORCEMENT LEARNING BY DENSITY RATIO ESTIMATION 审中-公开

    公开(公告)号：US20170213151A1

    公开(公告)日：2017-07-27

    申请号：US15329690

    申请日：2015-08-07

    Applicant: Okinawa Institute of Science and Technology School Corporation

    Inventor： Eiji UCHIBE ,  Kenji DOYA

    IPC: G06N99/00 ,  G06N7/00

    CPC classification number: G06N20/00 ,  G06N7/005

    Abstract: A method of inverse reinforcement learning for estimating cost and value functions of behaviors of a subject includes acquiring data representing changes in state variables that define the behaviors of the subject; applying a modified Bellman equation given by Eq. (1) to the acquired data: q(x)+gV(y)−V(x)=−1n{pi(y|x))/(p(y|x)} (1) where q(x) and V(x) denote a cost function and a value function, respectively, at state x, g represents a discount factor, and p(y|x) and pi(y|x) denote state transition probabilities before and after learning, respectively; estimating a density ratio pi(y|x)/p(y|x) in Eq. (1); estimating q(x) and V(x) in Eq. (1) using the least square method in accordance with the estimated density ratio pi(y|x)/p(y|x), and outputting the estimated q(x) and V(x).

Patent Agency Ranking